Metraipolis › archive › dc_415aff23be93
Causal Chain of Thought: Mitigating Attention Leakage via Context Isolation — arXiv:2610.31639
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.31639
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-25T08:35:42.171Z
- SHA-256 of the archived text
f0d1c9494434aa6944968d3a75f45416d9a7062e9d202a96b42ce621a219a7a2- Stable URL of this page
https://metraipolis.com/documento/dc_415aff23be93
How to cite
Causal Chain of Thought: Mitigating Attention Leakage via Context Isolation — arXiv:2610.31639 — arXiv (en), https://arxiv.org/abs/2610.31639 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_415aff23be93 (Metraipolis archive dc_415aff23be93, sha256 f0d1c9494434aa6944968d3a75f45416d9a7062e9d202a96b42ce621a219a7a2)
BibTeX
@misc{dc415aff23be93,
title = {Causal Chain of Thought: Mitigating Attention Leakage via Context Isolation — arXiv:2610.31639},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.31639},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_415aff23be93; sha256 f0d1c9494434aa6944968d3a75f45416d9a7062e9d202a96b42ce621a219a7a2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.31639. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Chain-of-thought (CoT) prompting elicits step-by-step rationales that appear to explain model predictions, but there is no guarantee these steps causally drive the final answer. In standard autoregressive generation, dense attention allows each reasoning step to attend to the full context, enabling the model to derive answers through direct lookup while generating plausible-sounding but post-hoc justifications. We introduce CausalCoT, an inference framework that enforces causal transparency by decomposing problems into a directed acyclic graph of atomic sub-questions, evaluating each node in an isolated context containing only its direct causal parents. This Markovian structure removes attention pathways to non-parent content, making downstream predictions sensitive to local reasoning rather than global context leakage. Across a diverse suite of reasoning benchmarks, CausalCoT preserves competitive predictive performance while improving explanation faithfulness, increasing causal sensitivity of intermediate reasoning steps by an average of 12 and up to 21 percentage points over the strongest baseline. The structured dependency graph additionally enables test-time interventions in which local corrections propagate predictably through downstream reasoning. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.31639 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-25T08:31:13.277Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).